{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:03:30Z","timestamp":1750309410795,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":20,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,21]],"date-time":"2024-10-21T00:00:00Z","timestamp":1729468800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,21]]},"DOI":"10.1145\/3627673.3679964","type":"proceedings-article","created":{"date-parts":[[2024,10,20]],"date-time":"2024-10-20T19:34:11Z","timestamp":1729452851000},"page":"3694-3698","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["MODRL-TA: A Multi-Objective Deep Reinforcement Learning Framework for Traffic Allocation in E-Commerce Search"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-0304-4483","authenticated-orcid":false,"given":"Peng","family":"Cheng","sequence":"first","affiliation":[{"name":"JD.com, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7115-8831","authenticated-orcid":false,"given":"Huimu","family":"Wang","sequence":"additional","affiliation":[{"name":"JD.com, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0259-233X","authenticated-orcid":false,"given":"Jinyuan","family":"Zhao","sequence":"additional","affiliation":[{"name":"JD.com, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1823-8335","authenticated-orcid":false,"given":"Yihao","family":"Wang","sequence":"additional","affiliation":[{"name":"JD.com, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-4647-3439","authenticated-orcid":false,"given":"Enqiang","family":"Xu","sequence":"additional","affiliation":[{"name":"JD.com, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3867-1128","authenticated-orcid":false,"given":"Yu","family":"Zhao","sequence":"additional","affiliation":[{"name":"JD.com, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3013-4264","authenticated-orcid":false,"given":"Zhuojian","family":"Xiao","sequence":"additional","affiliation":[{"name":"JD.com, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0102-9123","authenticated-orcid":false,"given":"Songlin","family":"Wang","sequence":"additional","affiliation":[{"name":"JD.com, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9586-4652","authenticated-orcid":false,"given":"Guoyu","family":"Tang","sequence":"additional","affiliation":[{"name":"JD.com, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4173-7650","authenticated-orcid":false,"given":"Lin","family":"Liu","sequence":"additional","affiliation":[{"name":"JD.com, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1610-6008","authenticated-orcid":false,"given":"Sulong","family":"Xu","sequence":"additional","affiliation":[{"name":"JD.com, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,21]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"International conference on machine learning. PMLR, 11--20","author":"Abels Axel","year":"2019","unstructured":"Axel Abels, Diederik Roijers, Tom Lenaerts, Ann Now\u00e9, and Denis Steckelmacher. 2019. Dynamic weights in multi-objective deep reinforcement learning. In International conference on machine learning. PMLR, 11--20."},{"key":"e_1_3_2_1_2_1","volume-title":"PID control","author":"\u00c5str\u00f6m Karl J","year":"2006","unstructured":"Karl J \u00c5str\u00f6m and Tore H\u00e4gglund. 2006. PID control. IEEE Control Systems Magazine, Vol. 1066 (2006)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_3_1","DOI":"10.1145\/2339530.2339718"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_4_1","DOI":"10.1145\/3018661.3018702"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_5_1","DOI":"10.1145\/2229012.2229038"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_6_1","DOI":"10.1007\/s10479-005-5724-z"},{"volume-title":"PID control","author":"Johnson Michael A","unstructured":"Michael A Johnson and Mohammad H Moradi. 2005. PID control. Springer.","key":"e_1_3_2_1_7_1"},{"key":"e_1_3_2_1_8_1","volume-title":"Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: EMNLP 2023 - Industry Track","author":"Li Mingming","year":"2023","unstructured":"Mingming Li, Chunyuan Yuan, Huimu Wang, Peng Wang, Jingwei Zhuo, Binbin Wang, Lin Liu, and Sulong Xu. 2023. Adaptive Hyper-parameter Learning for Deep Semantic Retrieval. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: EMNLP 2023 - Industry Track, Singapore, December 6--10, 2023, Mingxuan Wang and Imed Zitouni (Eds.). Association for Computational Linguistics, 775--782. https:\/\/aclanthology.org\/2023.emnlp-industry.72"},{"key":"e_1_3_2_1_9_1","volume-title":"Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602","author":"Mnih Volodymyr","year":"2013","unstructured":"Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Alex Graves, Ioannis Antonoglou, Daan Wierstra, and Martin Riedmiller. 2013. Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602 (2013)."},{"key":"e_1_3_2_1_10_1","volume-title":"Multi-objective deep reinforcement learning. arXiv preprint arXiv:1610.02707","author":"Mossalam Hossam","year":"2016","unstructured":"Hossam Mossalam, Yannis M Assael, Diederik M Roijers, and Shimon Whiteson. 2016. Multi-objective deep reinforcement learning. arXiv preprint arXiv:1610.02707 (2016)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_11_1","DOI":"10.1016\/j.engappai.2020.103915"},{"key":"e_1_3_2_1_12_1","volume-title":"Recogym: A reinforcement learning environment for the problem of product recommendation in online advertising. arXiv preprint arXiv:1808.00720","author":"Rohde David","year":"2018","unstructured":"David Rohde, Stephen Bonner, Travis Dunlop, Flavian Vasile, and Alexandros Karatzoglou. 2018. Recogym: A reinforcement learning environment for the problem of product recommendation in online advertising. arXiv preprint arXiv:1808.00720 (2018)."},{"volume-title":"Reinforcement learning: State-of-the-art","author":"Otterlo Martijn Van","unstructured":"Martijn Van Otterlo and Marco Wiering. 2012. Reinforcement learning and markov decision processes. In Reinforcement learning: State-of-the-art. Springer, 3--42.","key":"e_1_3_2_1_13_1"},{"key":"e_1_3_2_1_14_1","volume-title":"A Preference-oriented Diversity Model Based on Mutual-information in Re-ranking for E-commerce Search. arXiv preprint arXiv:2405.15521","author":"Wang Huimu","year":"2024","unstructured":"Huimu Wang, Mingming Li, Dadong Miao, Songlin Wang, Guoyu Tang, Lin Liu, Sulong Xu, and Jinghe Hu. 2024. A Preference-oriented Diversity Model Based on Mutual-information in Re-ranking for E-commerce Search. arXiv preprint arXiv:2405.15521 (2024)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_15_1","DOI":"10.1109\/TNNLS.2021.3070484"},{"unstructured":"Weixun Wang Junqi Jin Jianye Hao Chunjie Chen Chuan Yu Weinan Zhang Jun Wang Yixi Wang Han Li Jian Xu et al. 2018. Learning to advertise with adaptive exposure via constrained two-level reinforcement learning. arXiv preprint arXiv:1809.03149 (2018).","key":"e_1_3_2_1_16_1"},{"key":"e_1_3_2_1_17_1","volume-title":"A multi-agent reinforcement learning method for impression allocation in online display advertising. arXiv preprint arXiv:1809.03152","author":"Wu Di","year":"2018","unstructured":"Di Wu, Cheng Chen, Xun Yang, Xiujun Chen, Qing Tan, Jian Xu, and Kun Gai. 2018. A multi-agent reinforcement learning method for impression allocation in online display advertising. arXiv preprint arXiv:1809.03152 (2018)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_18_1","DOI":"10.1609\/aaai.v35i5.16580"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_19_1","DOI":"10.1145\/3626772.3661343"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_20_1","DOI":"10.1609\/aaai.v35i1.16156"}],"event":{"sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"],"acronym":"CIKM '24","name":"CIKM '24: The 33rd ACM International Conference on Information and Knowledge Management","location":"Boise ID USA"},"container-title":["Proceedings of the 33rd ACM International Conference on Information and Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3627673.3679964","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3627673.3679964","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:58:09Z","timestamp":1750294689000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3627673.3679964"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,21]]},"references-count":20,"alternative-id":["10.1145\/3627673.3679964","10.1145\/3627673"],"URL":"https:\/\/doi.org\/10.1145\/3627673.3679964","relation":{},"subject":[],"published":{"date-parts":[[2024,10,21]]},"assertion":[{"value":"2024-10-21","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}